{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"aa:b13c1257-d746-4027-8fc8-4892dc14701c:scicode","benchmark_id":"aa-scicode::1.0.1","subject":{"source_id":"b13c1257-d746-4027-8fc8-4892dc14701c","name":"GPT-5.5 (high)","model_id":"gpt-5.5::high","variant":"high","harness":null},"value":0.561342592592593,"unit":"fraction","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID b13c1257-d746-4027-8fc8-4892dc14701c; scicode"},"protocol":"Subproblem-level unit-test pass@1 over three repeats; AA methodology captured 2026-09-10; effort high","comparison_key":null}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":835,"available":167,"unknown":668,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":167,"self_reported":0,"observations":169,"unmatched_observations":2}},"collection":{"benchmark_id":"aa-scicode::1.0.1","status":"collected","source_url":"https://artificialanalysis.ai/models/gpt-5-6-sol","reason":"Exact AA UUID and field from the reviewed protocol snapshot; null does not prove whether AA ran the test."},"coverage_note":"Denominators are catalog model configurations × versioned registry entries. Basis counts count covered cells, not runs; measured and self_reported may overlap. Unmatched source identities remain in observations and never inflate catalog coverage."}